<!-- .github/pull_request_template.md -->
## Description
<!--
Please provide a clear, human-generated description of the changes in
this PR.
DO NOT use AI-generated descriptions. We want to understand your thought
process and reasoning.
-->
Added support for AWS Bedrock, and the models that are available there.
This was a contributor PR that was never finished, so now I polished it
up and made it work.
## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [x] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):
## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->
## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [x] **I have tested my changes thoroughly before submitting this PR**
- [x] **This PR contains minimal changes necessary to address the
issue/feature**
- [x] My code follows the project's coding standards and style
guidelines
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [ ] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] I have linked any relevant issues in the description
- [ ] My commits have clear and descriptive messages
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Added AWS Bedrock as a new LLM provider with support for multiple
authentication methods.
* Integrated three new AI models: Claude 4.5 Sonnet, Claude 4.5 Haiku,
and Amazon Nova Lite.
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
<!-- .github/pull_request_template.md -->
## Description
Make the pipeline cache mechanism optional, have it turned off by
default but use it for add and cognify like it has been used until now
## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [x] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):
## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [x] **I have tested my changes thoroughly before submitting this PR**
- [x] **This PR contains minimal changes necessary to address the
issue/feature**
- [x] My code follows the project's coding standards and style
guidelines
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] I have added necessary documentation (if applicable)
- [x] All new and existing tests pass
- [ x I have searched existing PRs to ensure this change hasn't been
submitted already
- [x] I have linked any relevant issues in the description
- [x] My commits have clear and descriptive messages
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Introduced pipeline caching across ingestion, processing, and custom
pipeline flows with per-run controls to enable or disable caching.
* Added an option for incremental loading in custom pipeline runs.
* **Behavior Changes**
* One pipeline path now explicitly bypasses caching by default to always
re-run when invoked.
* Disabling cache forces re-processing instead of early exit; cache
reset still enables re-execution.
* **Tests**
* Added tests validating caching, non-caching, and cache-reset
re-execution behavior.
* **Chores**
* Added CI job to run pipeline caching tests.
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
<!-- .github/pull_request_template.md -->
## Description
Add ability to use multi tenant multi user mode with Neo4j
## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):
## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->
## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [ ] **I have tested my changes thoroughly before submitting this PR**
- [ ] **This PR contains minimal changes necessary to address the
issue/feature**
- [ ] My code follows the project's coding standards and style
guidelines
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [ ] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] I have linked any relevant issues in the description
- [ ] My commits have clear and descriptive messages
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
## Release Notes
* **New Features**
* Multi-user support with per-dataset database isolation enabled by
default, allowing backend access control for secure data separation.
* Configurable database handlers via environment variables
(GRAPH_DATASET_DATABASE_HANDLER, VECTOR_DATASET_DATABASE_HANDLER) for
flexible deployment options.
* **Chores**
* Database schema migration to support per-user dataset database
configurations.
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
<!-- .github/pull_request_template.md -->
## Description
This pull request introduces edge‑centered payloads to the ingestion
process. Payloads are stored in the Triplet_text collection which is
compatible with the triplet_embedding memify pipeline.
Changes in This PR:
- Refactored custom edge handling, from now on they can be passed to the
add_data_points method so the ingestion is centralized and is happening
in one place.
- Added private methods to handle edge centered payload creation inside
the add_data_points.py
- Added unit tests to cover the new functionality
- Added integration tests
- Added e2e tests
Acceptance Criteria and Testing
Scenario 1:
-Set TRIPLET_EMBEDDING env var to True
-Run prune, add, cognify
-Verify the vector DB contains a non empty Triplet_text collection and
the number of triplets are matching with the number of edges in the
graph database
-Use the new triplet_completion search type and confirm it works
correctly.
Scenario 2:
-Set TRIPLET_EMBEDDING env var to True
-Run prune, add, cognify
-Verify the vector DB does not have the Triplet_text collection
-You should receive an error indicating that the Triplet_text is not
available
## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [x] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):
## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->
## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [x] **I have tested my changes thoroughly before submitting this PR**
- [x] **This PR contains minimal changes necessary to address the
issue/feature**
- [x] My code follows the project's coding standards and style
guidelines
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] I have added necessary documentation (if applicable)
- [x] All new and existing tests pass
- [x] I have searched existing PRs to ensure this change hasn't been
submitted already
- [x] I have linked any relevant issues in the description
- [x] My commits have clear and descriptive messages
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Triplet embeddings supported—embeddings created from graph edges plus
connected node text
* Ability to supply custom edges when adding data points
* New configuration toggle to enable/disable triplet embedding
* **Tests**
* Added comprehensive unit and end-to-end tests for edge-centered
payloads and triplet embedding
* New CI job to run the edge-centered payload e2e test
* **Bug Fixes**
* Adjusted server start behavior to surface process output in parent
logs
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Co-authored-by: Pavel Zorin <pazonec@yandex.ru>
<!-- .github/pull_request_template.md -->
## Description
<!--
Please provide a clear, human-generated description of the changes in
this PR.
DO NOT use AI-generated descriptions. We want to understand your thought
process and reasoning.
-->
This PR removes codify, and the code graph pipeline, out of the
repository. It also introduces a Custom Pipeline interface, which can be
used in the future to define custom pipelines.
## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [x] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):
## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->
## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [ ] **I have tested my changes thoroughly before submitting this PR**
- [ ] **This PR contains minimal changes necessary to address the
issue/feature**
- [ ] My code follows the project's coding standards and style
guidelines
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [ ] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] I have linked any relevant issues in the description
- [ ] My commits have clear and descriptive messages
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
<!-- .github/pull_request_template.md -->
## Description
<!--
Please provide a clear, human-generated description of the changes in
this PR.
DO NOT use AI-generated descriptions. We want to understand your thought
process and reasoning.
-->
Implement File-Based Version of the Redis Cache Adapter
Description and acceptance criteria:
This PR introduces a file-based cache adapter as an alternative to the
existing Redis-based adapter. It provides the same core functionality
for caching session data and maintaining context across multiple user
interactions but stores data locally in files instead of Redis.
Because the shared Kùzu lock mechanism relies on Redis, it is not
supported in this implementation. If a lock is configured, the adapter
will raise an error to prevent misconfiguration.
You can test this adapter by enabling caching with the following
settings:
caching=True
cache_backend="fs"
When running multiple searches in a session, the system should correctly
maintain conversational context. For example:
- What is XY?
- Are you sure?
- What was my first question?
In this case, the adapter should preserve previous user–Cognee
interactions within the cache file so that follow-up queries remain
context-aware.
## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [x] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):
## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->
## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [x] **I have tested my changes thoroughly before submitting this PR**
- [x] **This PR contains minimal changes necessary to address the
issue/feature**
- [x] My code follows the project's coding standards and style
guidelines
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] I have added necessary documentation (if applicable)
- [x] All new and existing tests pass
- [x] I have searched existing PRs to ensure this change hasn't been
submitted already
- [x] I have linked any relevant issues in the description
- [x] My commits have clear and descriptive messages
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
---------
Co-authored-by: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
Co-authored-by: hajdul88 <52442977+hajdul88@users.noreply.github.com>
<!-- .github/pull_request_template.md -->
## Description
<!--
Please provide a clear, human-generated description of the changes in
this PR.
DO NOT use AI-generated descriptions. We want to understand your thought
process and reasoning.
-->
Changed the key used for openai, since we changed the keys in the
secrets.
## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):
## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->
## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [ ] **I have tested my changes thoroughly before submitting this PR**
- [ ] **This PR contains minimal changes necessary to address the
issue/feature**
- [ ] My code follows the project's coding standards and style
guidelines
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [ ] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] I have linked any relevant issues in the description
- [ ] My commits have clear and descriptive messages
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
<!-- .github/pull_request_template.md -->
## Description
<!--
Please provide a clear, human-generated description of the changes in
this PR.
DO NOT use AI-generated descriptions. We want to understand your thought
process and reasoning.
-->
Added a load test to out codebase. The test runs N adds of a pdf, then
cognifies them and runs N searches. Cognify and the searches are
measured, with certain constraints on how fast they should be. We can
tweak the values if necessary, these are values for the gpt-5-mini
model.
## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):
## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->
## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [ ] **I have tested my changes thoroughly before submitting this PR**
- [ ] **This PR contains minimal changes necessary to address the
issue/feature**
- [ ] My code follows the project's coding standards and style
guidelines
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [ ] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] I have linked any relevant issues in the description
- [ ] My commits have clear and descriptive messages
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> Introduce a load test for S3 ingest, cognify, and concurrent searches
with timing thresholds, and wire it into CI.
>
> - **Tests**:
> - Add `cognee/tests/test_load.py` to measure end-to-end load: prunes
data/system, ingests from `s3://cognee-test-load-s3-bucket`, runs
`cognify` then concurrent GRAPH_COMPLETION searches, records timings
across reps, and asserts avg ≤ 8m and each run ≤ 10m.
> - **CI**:
> - Add `test-load` job in `.github/workflows/e2e_tests.yml`: installs
AWS deps, raises file descriptor limit, configures S3/env secrets, and
executes the new load test.
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
c7598122bb. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
…oviders support it
<!-- .github/pull_request_template.md -->
## Description
Enable multi user mode by default for supported graph and vector DBs
## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [x] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):
## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->
## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [ ] **I have tested my changes thoroughly before submitting this PR**
- [ ] **This PR contains minimal changes necessary to address the
issue/feature**
- [ ] My code follows the project's coding standards and style
guidelines
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [ ] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] I have linked any relevant issues in the description
- [ ] My commits have clear and descriptive messages
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
<!-- .github/pull_request_template.md -->
## Description
Add run_custom_pipeline to have a way to execute a custom collection of tasks in Cognee
## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):
## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->
## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [ ] **I have tested my changes thoroughly before submitting this PR**
- [ ] **This PR contains minimal changes necessary to address the
issue/feature**
- [ ] My code follows the project's coding standards and style
guidelines
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [ ] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] I have linked any relevant issues in the description
- [ ] My commits have clear and descriptive messages
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
